@article{visionasadialectunifyingvisual,
  title = {Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations},
  author = {Jiaming Han and Hao Chen and Yang Zhao and Hanyu Wang and Qi Zhao and Ziyan Yang and Hao He and Xiangyu Yue and Lu Jiang},
  year = {2025},
  eprint = {2506.18898},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.18898v1},
}